© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29839
    Prev
    Next
    INDEX
    Explanations

    Some [noun referring to something]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sorts
    -0.10
     residual
    -0.10
    -o
    -0.09
    thers
    -0.09
     Boutique
    -0.08
     types
    -0.08
     kinds
    -0.08
    -tw
    -0.08
     constitu
    -0.08
     interf
    -0.08
    POSITIVE LOGITS
     Relevant
    0.11
    owy
    0.11
     Useful
    0.11
     fucking
    0.11
     Griffin
    0.11
     Fucking
    0.10
    quine
    0.10
    اØ
    0.09
    rox
    0.09
     Thoughts
    0.09
    Activations Density 0.119%

    No Known Activations